Building and Pilot Testing a Couples-based Smartphone Systems to Address Alcohol Use Disorder: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Building and Pilot Testing a Couples-based Smartphone Systems to Address Alcohol Use Disorder (NCT04059549), a randomized na study. The primary outcome is Number of Participants With no Heavy Drinking.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group behavioral study comparing PartnerCHESS with A-CHESS. The registry lists the allocation as randomized and masking as none. It records the phase as NA and enrollment as 68. The study status is completed; the recorded start date is 2020-11-17 and primary completion date is 2021-09-29.

The two arms differed in the services described for patients and partners. A-CHESS participants received the A-CHESS app on a smartphone. PartnerCHESS participants received A-CHESS services plus learning modules and resources from Alcohol-based Couple Therapy. The project summary describes the system as serving patients, partners, and clinicians, and says that a Clinician Report was part of the proposed system. The registry record does not describe the extent to which every planned system component was used during the pilot.

The project had a development and pilot-testing purpose. Its stated aims included integrating A-CHESS with features of Alcohol-based Couple Therapy, conducting a small randomized clinical trial, estimating an effect, and refining the protocol, procedures, recruitment strategy, measurements, and operations for a possible larger trial. It also aimed to decide whether to pursue an R01 application and, if so, plan for it.

The primary outcome was assessed at baseline and at 2, 4, and 6 months. Other outcomes listed include psychological distress, relationship satisfaction, perceptions of family environment, commitment to sobriety, and peer support. The registry record does not report further details about random sequence generation, allocation concealment, recruitment, adherence, or the statistical analysis plan.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With no Heavy Drinking, measured over baseline, 2, 4, and 6 months.

The primary endpoint is titled Number of Participants With no Heavy Drinking. It is a count of participants meeting the endpoint at each scheduled measurement, rather than a continuous measure of drinking quantity. The registry describes a timeline follow-back interview covering the past 60 days at each measurement. A risky drinking day was defined as greater than 4 drinks for men and greater than 3 drinks for women in 2 hours.

This kind of endpoint is used to describe whether participants experienced heavy drinking during a defined recall period. The count is repeated at baseline and at 2, 4, and 6 months, so it can describe the outcome at several points during the study. A count alone does not show the proportion of all participants who met the definition unless the relevant denominator is also given, and it does not describe how much drinking occurred among participants who had risky drinking days.

The registry record does not give the observed counts at these time points, define a single summary comparison across them, or report an effect estimate and uncertainty interval. The outcome definition therefore explains what was intended to be measured, but the posted record does not establish what the study found.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Randomization assigns participants to study groups using a chance-based process. In general, this can reduce systematic differences between groups at the start of a study, though chance imbalances can still occur, particularly in a pilot. The registry lists this study as randomized and parallel-group. It does not report how the random sequence was generated, whether allocation was concealed, or whether any stratification was used, so those methods cannot be characterized further.

What does the parallel-group design mean?

In a parallel design, participants are assigned to one group and receive that group’s intervention during the study, rather than crossing over between interventions. Here, the registry describes an A-CHESS group and a PartnerCHESS group. The recorded masking is none, meaning the registry does not describe the study as masked. It does not specify whether outcome assessors or analysts were also unmasked. In general, masking can limit the influence of expectations on treatment delivery or outcome assessment, but it is not possible to determine from the record how those considerations were addressed.

How should the repeated endpoint be understood?

The primary endpoint is a participant count measured at baseline and at 2, 4, and 6 months. Each measure uses a timeline follow-back interview for the past 60 days, with risky drinking days defined using the sex-specific drink thresholds in the endpoint description. Repeated measurements can show how an outcome changes over time, but they also create analysis choices. A comparison at each time point answers a different question from a model that estimates an overall group difference or a difference in trajectories. The registry record does not say which comparison was planned or performed.

General statistical explanation: observations from the same participant over time are usually related rather than independent. A longitudinal analysis can account for that relationship, while a simple analysis that treats every measurement as unrelated may not. The appropriate method depends on the study question, outcome form, and missing-data pattern. The registry record does not report a model, its assumptions, or any diagnostic checks.

What does a count endpoint tell the reader?

A count gives the number of participants meeting the endpoint, but interpretation also depends on how many participants were assessed. If the number assessed changes between time points, the same count could reflect a different proportion of those measured. The registry record does not report the primary outcome counts or assessment denominators, so neither the counts nor the proportions can be interpreted from this record. The endpoint title refers to participants with no heavy drinking, while the description defines a risky drinking day; the record does not give additional operational detail about coding the participant-level status.

How should planning calculations be read?

General statistical explanation: power is the probability that a planned analysis will detect an effect of a specified size under stated assumptions. Sample-size calculations are planning tools, not descriptions of what a completed study observed. The planning assumptions recorded for this study use a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is described as a fraction of the observed effect. The record does not give a sample-size justification for the trial itself, nor does it report the effect estimates needed to interpret any planning illustration. Such illustrations are not observed power.

A confidence interval, in general, communicates uncertainty around an estimate. A narrow interval indicates greater precision under the chosen model, while a wide interval indicates greater uncertainty. A p-value alone does not describe the size or precision of an effect. The registry record does not report confidence intervals or p-values for the primary endpoint, so no conclusion about statistical significance or precision can be drawn from the listed design information.

What analysis information is absent?

The registry record lists no analysis entries. It does not report an analysis population, adjustment variables, a method for handling repeated measures, an approach to missing data, or a multiplicity strategy for multiple outcomes and assessment times. It also does not report interim analyses. These omissions mean that the statistical methods used to produce any results cannot be reconstructed from the record. General good practice is to interpret estimates in light of the prespecified question, model assumptions, missingness, and analysis population; those details are not available in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The primary endpoint has repeated assessment times, and the registry also lists secondary outcomes covering psychological distress, relationship satisfaction, family environment, commitment to sobriety, and peer support. Testing several outcomes or time points can increase the chance of at least one apparently notable result when many comparisons are made. General statistical practice may address this through a prespecified primary contrast, adjusted testing, or an emphasis on estimation and uncertainty. The registry record does not report a multiplicity plan, so it is not possible to tell whether or how multiple comparisons were handled.

The registry lists 9 outcome measures and 0 analysis entries. It does not identify an analysis population, such as all randomized participants or only participants with available follow-up data. Nor does it describe how missing interviews, withdrawals, or incomplete measurements were handled. These details matter because the number and characteristics of participants with outcome data may differ across assessment times or groups.

General explanation: missing data can affect estimates when the chance that a measurement is absent is related to participants’ outcomes or circumstances. Methods for handling missingness rely on assumptions, and those assumptions should be described alongside the analysis. The registry record does not report a missing-data method or the amount of missing primary outcome data. No inference about completeness or bias from missing observations can therefore be made.

The project was intended as a pilot to estimate an effect and refine procedures for a possible larger trial. The registry record does not report a formal statistical analysis plan, interim analyses, or rules for including participants in each analysis. This limits assessment of whether the reported analysis, if any, followed a prespecified approach.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry lists serious adverse event figures for the two groups. For A-CHESS, 30 are listed at risk, with 0 affected by serious adverse events, 0 affected by other adverse events, and 0 deaths. For PartnerCHESS, 36 are listed at risk, with 0 serious adverse events, 0 other adverse events, and 0 deaths. No top serious adverse event terms are listed.

These are event counts, not a comparison adjusted for exposure time or other differences between groups. The registry record does not explain how the at-risk counts relate to the enrollment total, how adverse events were collected, or the observation period for these safety figures. The counts should therefore be read as the figures recorded, rather than as proof that no adverse events occurred outside the registry’s reporting scope.

General statistical explanation: when no events are recorded, the data do not establish that the true event risk is zero. Rare events can remain unobserved in a study, and estimates based on small groups can be imprecise. The record does not report uncertainty intervals or a comparative safety analysis. These figures alone cannot establish whether one intervention is safer than the other.

12. What the Result Does, and Does Not, Mean

The record documents a randomized pilot comparing a smartphone-based system that adds couple-therapy learning modules and resources to A-CHESS with A-CHESS alone. It describes an intended outcome concerning participants with no heavy drinking and repeated assessments through 6 months. It also records secondary outcomes related to psychological and relationship measures. These details clarify the study question and the information the investigators intended to gather.

The record does not report primary outcome counts, between-group estimates, uncertainty intervals, or inferential results. It therefore does not establish the direction or magnitude of any difference in heavy drinking between the groups. Missing results in this record should not be interpreted as showing that the systems had equal outcomes, nor as evidence that one approach performed better.

The study was presented as a pilot whose aims included estimating an effect and refining procedures for a possible larger trial. Pilot estimates are useful for learning about implementation and informing later research, but their precision can be limited. The registry record does not include a sample-size justification, and the enrollment figure by itself does not indicate the precision of an outcome estimate.

The endpoint captures a participant-level classification over a past-60-day recall period at each measurement. It does not, by itself, describe all aspects of alcohol use, recovery, relationship functioning, or the experience of participants and partners. The listed secondary outcomes broaden the topics considered, but their results are not reported in the registry record.

In general, evidence from a randomized study is interpreted by combining the estimated group contrast with its uncertainty, the study methods, and the completeness of follow-up. Here, the design and outcome definitions can be described, but the absence of reported outcome analyses prevents an assessment of treatment effects. No medical conclusion or treatment recommendation follows from the information recorded.

13. Why This Trial Matters Statistically

This trial is statistically notable as a randomized pilot of an intervention designed for patients and partners, rather than a study focused only on a patient-facing app. The comparison isolates the addition of learning modules and resources from Alcohol-based Couple Therapy to A-CHESS services, as described in the registry. Its stated purpose was also methodological: estimate an effect and refine recruitment, measurement, procedures, and operations for a possible larger randomized trial.

That distinction matters for interpreting the role of pilot data. A pilot can help identify whether an intervention and its assessment procedures are workable and can produce preliminary estimates to inform later research. General statistical reasoning cautions against treating such estimates as definitive, particularly when precision is not reported. The registry record does not provide an effect estimate or uncertainty interval, so it does not permit assessment of precision in this case.

The outcome schedule also raises useful design questions for future work. The primary measure was assessed at multiple times, and the study included several secondary outcomes. A larger trial would need a clearly defined primary comparison, a plan for repeated measurements and multiplicity, and transparent reporting of denominators and missing data. The registry record does not say how these issues were handled in this pilot.

The study’s significance for statistical education lies in the difference between a well-described research question and a reported result. The registry describes randomization, intervention groups, endpoint definitions, and a pilot objective. Without outcome values and analyses, however, those design details cannot answer whether the groups differed. Clear registration of methods and complete reporting of estimates would be needed for readers to evaluate the findings and the uncertainty around them.

14. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record describes the study design and intended measurements but does not include primary outcome results. It therefore lacks the counts needed to assess the endpoint or compare the groups. No effect estimates, confidence intervals, or p-values are reported, and the registry lists 0 analysis entries. The result cannot be evaluated statistically from the information recorded.

The main endpoint is assessed at multiple times, but the record does not define a single primary contrast across baseline and follow-up. It does not describe whether the analyses compared groups at each time, modeled change over time, or used another approach. It also does not report the statistical model, assumptions, or any adjustment for multiple comparisons.

The record does not report the number of participants with endpoint data at each assessment, the amount of missing data, or how missing observations were handled. The analysis population and the relationship between the safety at-risk counts and enrollment are also not explained. These gaps limit interpretation of both outcome completeness and the safety figures.

Further design details are not reported in the registry record, including random sequence generation, allocation concealment, recruitment procedures, eligibility criteria, adherence, and whether outcome assessors were masked. The recorded masking is none, but the record does not specify masking of assessors or analysts. The description does not establish how fully the intended clinician-facing features were implemented during the pilot.

Finally, the project was framed as a pilot to inform refinement and potential future research. The record does not report a sample-size justification or precision target. Its enrollment and design description should therefore be read as context for the pilot, not as enough information to judge the precision, generalizability, or clinical importance of an effect.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Building and Pilot Testing a Couples-based Smartphone Systems to Address Alcohol Use Disorder — NCT04059549.
• Registry record last updated 2025-04-22; status last verified 2022-11.
• Results first posted 2022-12-07.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

NCT04059549 is a completed randomized, parallel-group behavioral pilot comparing PartnerCHESS with A-CHESS. The registry records 68 enrolled participants, no masking, and a phase of NA. The recorded study start was 2020-11-17, and primary completion was 2021-09-29.

The primary outcome was the number of participants with no heavy drinking, assessed at baseline and at 2, 4, and 6 months using a timeline follow-back interview for the past 60 days. The project aimed to develop PartnerCHESS, pilot-test it, estimate an effect, and refine procedures for possible larger research. The record lists secondary outcomes but does not report primary outcome estimates, analyses, or a statistical analysis plan. It records 0 serious adverse events and 0 deaths in each group, with 30 listed at risk for A-CHESS and 36 for PartnerCHESS.